Work Automations
Private held-out set; API mode; 50 steps; strict pass/fail
- 01
- 02
- 03
- 04
- 05
Gemini 4 Argon
Across the task benchmarks we track, Gemini 4 Argon’s strongest relative results are in work automations and knowledge work. On AutomationBench 1.0.6, it scores 51.29%, ranking #2 among 17 models with reported results in our dataset.
Updated: Data as of:
🥇
Strongest results
| Benchmark | Measures | Score |
|---|---|---|
| Agent Index ↗v1.2 Preview | Overall agent capability | 67.3 / 100#8 of 26 |
| LiveBench: Data Analysis ↗2.0 / 2026-10-25 | Data analysis | 85.2%#1 of 25 |
| LiveBench: Reasoning ↗2.0 / 2026-10-25 | Reasoning with LiveBench | 95.1%#1 of 25 |
| AutomationBench-AA ↗1.0.6 / AA private 657 | Work automations | 77.5%#2 of 55 |
Model details
| Model | Gemini 4 Argon |
|---|---|
| Agent Index v1.2 | 67.3 / 100 · Rank 8 · Preview |
| Creator | Google (opens in a new tab) |
| Availability | Proprietary |
| Context size | 1,000,000 tokens (opens in a new tab) |
| Max output | 65,536 tokens (opens in a new tab) |
| Knowledge cutoff | Not reported |
| License | Not reported |
Pricing and performance
Per provider and reported configuration. Prices are USD per 1M tokens.
| Provider / configuration | Contexttokens | InputUSD / 1M tokens | OutputUSD / 1M tokens | LatencyTTFT · seconds | Speedtokens / sec |
|---|---|---|---|---|---|
| Gemini 4 Argon (high) (Vertex) | 1,000,000 | $4.00 (opens in a new tab) | $20.00 (opens in a new tab) | 44.081 (opens in a new tab) | 83.574 (opens in a new tab) |
| Gemini 4 Argon (high) AI Studio | 1,000,000 | $4.00 (opens in a new tab) | $20.00 (opens in a new tab) | 47.152 (opens in a new tab) | 87.964 (opens in a new tab) |
| Gemini 4 Argon (high) AI Studio (1M output) | 1,000,000 | $4.00 (opens in a new tab) | $20.00 (opens in a new tab) | Not reported | Not reported |
Benchmark performance
Gemini 4 Argon in color, alongside leading models. Latest stored reports, best effort per report date.
AutomationBench 1.0.6 ↗
Knowledge Work
220 tasks; Stirrup agent; pairwise Elo
- 01
- 02
- 03
- 04
- 05
- 12
Reported benchmarks
All published results in our dataset, with versions, evaluation settings, and sources.
| Benchmark | Score | Evaluation setup | Source |
|---|---|---|---|
| AA-Briefcase1.1 / combined EloCombined Elo · Higher is better | 1,484 Elo | selection: best reported configuration per release · Gemini 4 Argon (high) · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 50.08% | Gemini 4 Argon (Medium); private held-out 657 tasks; API mode; 50-step cap; strict completion | Zapier ↗ (opens in a new tab)benchmark publisher |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 51.29% | Gemini 4 Argon (High); private held-out 657 tasks; API mode; 50-step cap; strict completion | Zapier ↗ (opens in a new tab)benchmark publisher |
| AutomationBench-AA1.0.6 / AA private 657Objectives completed without guardrail violations · Higher is better | 77.5% | high | Artificial Analysis (opens in a new tab)independent |
| GDP.pdf100 tasks / All-pass / five attemptsAccuracy · Higher is better | 21.8% | selection: best reported configuration per release · Gemini 4 Argon (high) · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,630.66 Elo | Gemini 4 Argon (High); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| HLE-Diamond1,000 questions / no toolsAccuracy · Higher is better | 56.7% | selection: best reported configuration per release · Gemini 4 Argon (High) · No tools | Artificial Analysis (opens in a new tab)independent |
| Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better | 57.1% | High effort; AA methodology: 2158 text-only questions; pass@1; no tools; GPT-5.6 Luna medium judge. · subset: text · No tools | Artificial Analysis (opens in a new tab)independent |
| LiveBench: Agentic2.0 / 2026-10-25Accuracy · Higher is better | 61.2% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: agentic | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Browser Use2.0 / 2026-10-25Accuracy · Higher is better | 82.8% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: browser-use | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Coding2.0 / 2026-10-25Accuracy · Higher is better | 89.7% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Data Analysis2.0 / 2026-10-25Accuracy · Higher is better | 85.2% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: data-analysis | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Design2.0 / 2026-10-25Accuracy · Higher is better | 73.7% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: design | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Reasoning2.0 / 2026-10-25Accuracy · Higher is better | 95.1% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: reasoning | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Research2.0 / 2026-10-25Accuracy · Higher is better | 83.1% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: research | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| Terminal-Bench4.0 / mini-swe-agentTask success · Higher is better | 57.071% | harness: mini-swe-agent · repeats: 3 · selection: best reported configuration per release · Gemini 4 Argon (High) | Artificial Analysis (opens in a new tab)independent |